telegraf-influxDB-grafana/alertmanager/alert.rules

groups:
- name: targets
  rules:
  - alert: monitor_service_down
    expr: up == 0
    for: 30s
    labels:
      severity: critical
    annotations:
      summary: "Monitor service non-operational"
      description: "Service {{ $labels.instance }} is down."

## FOR HOST ##################################################################

- name: host
  rules:
  - alert: HostHighCpuLoad
    expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[2m])) * 100) > 80
    for: 0m
    labels:
      severity: warning
    annotations:
      summary: Host high CPU load (instance {{ $labels.instance }})
      description: "CPU load is > 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: high_memory_load
    expr: (sum(node_memory_MemTotal_bytes) - sum(node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) ) / sum(node_memory_MemTotal_bytes) * 100 > 85
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server memory is almost full"
      description: "Docker host memory usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."

  - alert: HostPhysicalComponentTooHot
    expr: node_hwmon_temp_celsius > 75
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Host physical component too hot (instance {{ $labels.instance }})
      description: "Physical hardware component too hot\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostSwapIsFillingUp
    expr: (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes)) * 100 > 80
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Host swap is filling up (instance {{ $labels.instance }})
      description: "Swap is filling up (>80%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: high_storage_load
    expr: (node_filesystem_size_bytes{fstype="aufs"} - node_filesystem_free_bytes{fstype="aufs"}) / node_filesystem_size_bytes{fstype="aufs"}  * 100 > 85
    for: 30s
    labels:
      severity: warning
    annotations:
      summary: "Server storage is almost full"
      description: "Docker host storage usage is {{ humanize $value}}%. Reported by instance {{ $labels.instance }} of job {{ $labels.job }}."

  - alert: HostOutOfMemory
    expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Host out of memory (instance {{ $labels.instance }})
      description: "Node memory is filling up (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostUnusualNetworkThroughputIn
    expr: sum by (instance) (rate(node_network_receive_bytes_total[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Host unusual network throughput in (instance {{ $labels.instance }})
      description: "Host network interfaces are probably receiving too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostUnusualNetworkThroughputOut
    expr: sum by (instance) (rate(node_network_transmit_bytes_total[2m])) / 1024 / 1024 > 100
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: Host unusual network throughput out (instance {{ $labels.instance }})
      description: "Host network interfaces are probably sending too much data (> 100 MB/s)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostOutOfDiskSpace
    expr: (node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes < 10 and ON (instance, device, mountpoint) node_filesystem_readonly == 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Host out of disk space (instance {{ $labels.instance }})
      description: "Disk is almost full (< 10% left)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

## FOR RAID ##########################################################

  - alert: HostRaidArrayGotInactive
    expr: node_md_state{state="inactive"} > 0
    for: 0m
    labels:
      severity: critical
    annotations:
      summary: Host RAID array got inactive (instance {{ $labels.instance }})
      description: "RAID array {{ $labels.device }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: HostRaidDiskFailure
    expr: node_md_disks{state="failed"} > 0
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Host RAID disk failure (instance {{ $labels.instance }})
      description: "At least one device in RAID array on {{ $labels.instance }} failed. Array {{ $labels.md_device }} needs attention and possibly a disk swap\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"


## FOR CONTAINERS #####################################################

- name: containers
  rules:
  - alert: nextcloud_down
    expr: absent(container_memory_usage_bytes{name="jenkins"})
    for: 30s
    labels:
      severity: critical
    annotations:
      summary: "Nextcloud down"
      description: "Nextcloud container is down for more than 30 seconds."

  - alert: ContainerCpuUsage
    expr: (sum(rate(container_cpu_usage_seconds_total{name!=""}[3m])) BY (instance, name) * 100) > 80
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Container CPU usage (instance {{ $labels.instance }})
      description: "Container CPU usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: ContainerMemoryUsage
    expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
    for: 2m
    labels:
      severity: warning
    annotations:
      summary: Container Memory usage (instance {{ $labels.instance }})
      description: "Container Memory usage is above 80%\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"


## FOR NGINX ##########################################################

- name: nginx
  rules:
  - alert: NginxHighHttp4xxErrorRate
    expr: sum(rate(nginx_http_requests_total{status=~"^4.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: Nginx high HTTP 4xx error rate (instance {{ $labels.instance }})
      description: "Too many HTTP requests with status 4xx (> 5%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"

  - alert: NginxHighHttp5xxErrorRate
    expr: sum(rate(nginx_http_requests_total{status=~"^5.."}[1m])) / sum(rate(nginx_http_requests_total[1m])) * 100 > 5
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: Nginx high HTTP 5xx error rate (instance {{ $labels.instance }})
      description: "Too many HTTP requests with status 5xx (> 5%)\n  VALUE = {{ $value }}\n  LABELS = {{ $labels }}"